Search Results for author:
Found 151 papers, 68 papers with code
Learning to Focus on the Foreground for Temporal Sentence Grounding
Then, we develop a self-supervised coarse-to-fine paradigm to learn to locate the most query-relevant patch in each frame and aggregate them among the video for final grounding.
Implicit Relation Linking for Question Answering over Knowledge Graph
In this paper, we propose an implicit RL method called ImRL, which links relation phrases in NL to relation paths in KG.
融合XLM词语表示的神经机器译文自动评价方法(Neural Automatic Evaluation of Machine Translation Method Combined with XLM Word Representation)
“机器译文自动评价对机器翻译的发展和应用起着重要的促进作用, 它一般通过计算机器译文和人工参考译文的相似度来度量机器译文的质量。该文通过跨语种预训练语言模型XLM将源语言句子、机器译文和人工参考译文映射到相同的语义空间, 结合分层注意力和内部注意力提取源语言句子与机器译文、机器译文与人工参考译文以及源语言句子与人工参考译文之间差异特征, 并将其融入到基于Bi-LSTM神经译文自动评价方法中。在WMT’19译文自动评价数据集上的实验结果表明, 融合XLM词语表示的神经机器译文自动评价方法显著提高了其与人工评价的相关性。”
HERTA: A High-Efficiency and Rigorous Training Algorithm for Unfolded Graph Neural Networks
In this paper, we propose HERTA: a High-Efficiency and Rigorous Training Algorithm for Unfolded GNNs that accelerates the whole training process, achieving a nearly-linear time worst-case training guarantee.
KnowLA: Enhancing Parameter-efficient Finetuning with Knowledgeable Adaptation
Parameter-efficient finetuning (PEFT) is a key technique for adapting large language models (LLMs) to downstream tasks.
CasSR: Activating Image Power for Real-World Image Super-Resolution
In particular, we develop a cascaded controllable diffusion model that aims to optimize the extraction of information from low-resolution images.
RangeLDM: Fast Realistic LiDAR Point Cloud Generation
Autonomous driving demands high-quality LiDAR data, yet the cost of physical LiDAR sensors presents a significant scaling-up challenge.
Near-Interpolators: Rapid Norm Growth and the Trade-Off between Interpolation and Generalization
Under a random matrix theoretic assumption on the data distribution and an eigendecay assumption on the data covariance matrix $\boldsymbol{\Sigma}$, we demonstrate that any near-interpolator exhibits rapid norm growth: for $\tau$ fixed, $\boldsymbol{\beta}$ has squared $\ell_2$-norm $\mathbb{E}[\|{\boldsymbol{\beta}}\|_{2}^{2}] = \Omega(n^{\alpha})$ where $n$ is the number of samples and $\alpha >1$ is the exponent of the eigendecay, i. e., $\lambda_i(\boldsymbol{\Sigma}) \sim i^{-\alpha}$.
LTGC: Long-tail Recognition via Leveraging LLMs-driven Generated Content
Long-tail recognition is challenging because it requires the model to learn good representations from tail categories and address imbalances across all categories.
Generative 3D Part Assembly via Part-Whole-Hierarchy Message Passing
Subsequently, we transform the point cloud using the latent poses, feeding it to the part encoder for aggregating super-part information and reasoning about part relationships to predict all part poses.
InvariantOODG: Learning Invariant Features of Point Clouds for Out-of-Distribution Generalization
The convenience of 3D sensors has led to an increase in the use of 3D point clouds in various applications.
DHGCN: Dynamic Hop Graph Convolution Network for Self-Supervised Point Cloud Learning
Recent works attempt to extend Graph Convolution Networks (GCNs) to point clouds for classification and segmentation tasks.
Knowledge Graph Error Detection with Contrastive Confidence Adaption
Knowledge graphs (KGs) often contain various errors.
Conflict Detection for Temporal Knowledge Graphs:A Fast Constraint Mining Algorithm and New Benchmarks
Temporal facts, which are used to describe events that occur during specific time periods, have become a topic of increased interest in the field of knowledge graph (KG) research.
Generating Explanations to Understand and Repair Embedding-based Entity Alignment
In this paper, we present the first framework that can generate explanations for understanding and repairing embedding-based EA results.
Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking
Recent work by Power et al. (2022) highlighted a surprising "grokking" phenomenon in learning arithmetic tasks: a neural net first "memorizes" the training set, resulting in perfect training accuracy but near-random test accuracy, and after training for sufficiently longer, it suddenly transitions to perfect test accuracy.
Evolutionary City: Towards a Flexible, Agile and Symbiotic System
This paper introduces a novel approach, aiming to enable cities to evolve and respond more effectively to such dynamic demand.
Understanding Deep Representation Learning via Layerwise Feature Compression and Discrimination
To the best of our knowledge, this is the first quantitative characterization of feature evolution in hierarchical representations of deep linear networks.
Continual Event Extraction with Semantic Confusion Rectification
We study continual event extraction, which aims to extract incessantly emerging event information while avoiding forgetting.
How Do Transformers Learn In-Context Beyond Simple Functions? A Case Study on Learning with Representations
Through extensive probing and a new pasting experiment, we further reveal several mechanisms within the trained transformers, such as concrete copying behaviors on both the inputs and the representations, linear ICL capability of the upper layers alone, and a post-ICL representation selection mechanism in a harder mixture setting.
Benign Overfitting and Grokking in ReLU Networks for XOR Cluster Data
Second, they can undergo a period of classical, harmful overfitting -- achieving a perfect fit to training data with near-random performance on test data -- before transitioning ("grokking") to near-optimal generalization later in training.
Bias Amplification Enhances Minority Group Performance
Neural networks produced by standard training are known to suffer from poor accuracy on rare subgroups despite achieving high accuracy on average, due to the correlations between certain spurious features and labels.
Dense Object Grounding in 3D Scenes
Localizing objects in 3D scenes according to the semantics of a given natural language is a fundamental yet important task in the field of multimedia understanding, which benefits various real-world applications such as robotics and autonomous driving.
MDCS: More Diverse Experts with Consistency Self-distillation for Long-tailed Recognition
In the analysis and ablation study, we demonstrate that our method compared with previous work can effectively increase the diversity of experts, significantly reduce the variance of the model, and improve recognition accuracy.
Ranked #5 on
Long-tail Learning
on CIFAR-10-LT (ρ=50)
3DHacker: Spectrum-based Decision Boundary Generation for Hard-label 3D Point Cloud Attack
With the maturity of depth sensors, the vulnerability of 3D point cloud models has received increasing attention in various applications such as autonomous driving and robot navigation.
IR Design for Application-Specific Natural Language: A Case Study on Traffic Data
In the realm of software applications in the transportation industry, Domain-Specific Languages (DSLs) have enjoyed widespread adoption due to their ease of use and various other benefits.
Are Neurons Actually Collapsed? On the Fine-Grained Structure in Neural Representations
This appears to suggest that the last-layer representations are completely determined by the labels, and do not depend on the intrinsic structure of input distribution.
What Makes Entities Similar? A Similarity Flooding Perspective for Multi-sourced Knowledge Graph Embeddings
In this paper, we provide a similarity flooding perspective to explain existing translation-based and aggregation-based EA models.
Joint Pre-training and Local Re-training: Transferable Representation Learning on Multi-source Knowledge Graphs
We pre-train a large teacher KG embedding model over linked multi-source KGs and distill knowledge to train a student model for a task-specific KG.
The Law of Parsimony in Gradient Descent for Learning Deep Linear Networks
Second, it allows us to better understand deep representation learning by elucidating the linear progressive separation and concentration of representations from shallow to deep layers.
Robust Sparse Mean Estimation via Incremental Learning
This paper presents a simple mean estimator that overcomes both challenges under moderate conditions: it runs in near-linear time and memory (both with respect to the ambient dimension) while requiring only $\tilde O(k)$ samples to recover the true mean.
Serial Contrastive Knowledge Distillation for Continual Few-shot Relation Extraction
Continual few-shot relation extraction (RE) aims to continuously train a model for new relations with few labeled training data, of which the major challenges are the catastrophic forgetting of old relations and the overfitting caused by data sparsity.
Improving Continual Relation Extraction by Distinguishing Analogous Semantics
To address this issue, we propose a novel continual extraction model for analogous relations.
MixPro: Data Augmentation with MaskMix and Progressive Attention Labeling for Vision Transformer
TransMix uses unreliable attention maps to compute mixed attention labels that can affect the model.
Ranked #1 on
Data Augmentation
on ImageNet
Density-Insensitive Unsupervised Domain Adaption on 3D Object Detection
Recently, few works attempt to tackle the domain gap in objects, but still fail to adapt to the gap of varying beam-densities between two domains, which is critical to mitigate the characteristic differences of the LiDAR collectors.
Deep Active Alignment of Knowledge Graph Entities and Schemata
With deep learning, it learns the embeddings of entities, relations and classes, and jointly aligns them in a semi-supervised manner.
Heterogeneous Federated Knowledge Graph Embedding Learning and Unlearning
To cope with the drift between local optimization and global convergence caused by data heterogeneity, we propose mutual knowledge distillation to transfer local knowledge to global, and absorb global knowledge back.
LS-DYNA Machine Learning-based Multiscale Method for Nonlinear Modeling of Short Fiber-Reinforced Composites
In this work, we present a machine learning-based multiscale method by integrating injection molding-induced microstructures, material homogenization, and Deep Material Network (DMN) in the finite element simulation software LS-DYNA for structural analysis of SFRC.
Open-world Story Generation with Structured Knowledge Enhancement: A Comprehensive Survey
Storytelling and narrative are fundamental to human experience, intertwined with our social and cultural engagement.
Lifelong Embedding Learning and Transfer for Growing Knowledge Graphs
We consider knowledge transfer and retention of the learning on growing snapshots of a KG without having to learn embeddings from scratch.
Learning Latent Part-Whole Hierarchies for Point Clouds
The decoder takes the latent variable and the feature from the encoder as an input and predicts the per-point part distribution at the top level.
EventEA: Benchmarking Entity Alignment for Event-centric Knowledge Graphs
Towards a critical evaluation of embedding-based entity alignment methods, we construct a new dataset with heterogeneous relations and attributes based on event-centric KGs.
Museformer: Transformer with Fine- and Coarse-Grained Attention for Music Generation
A recent trend is to use Transformer or its variants in music generation, which is, however, suboptimal, because the full attention cannot efficiently model the typically long music sequences (e. g., over 10, 000 tokens), and the existing models have shortcomings in generating musical repetition structures.
Implicit Bias in Leaky ReLU Networks Trained on High-Dimensional Data
In this work, we investigate the implicit bias of gradient flow and gradient descent in two-layer fully-connected neural networks with leaky ReLU activations when the training data are nearly-orthogonal, a common property of high-dimensional data.
Large-scale Entity Alignment via Knowledge Graph Merging, Partitioning and Embedding
Therefore, in this work, we propose a scalable GNN-based entity alignment approach to reduce the structure and alignment loss from three perspectives.
Inductive Knowledge Graph Reasoning for Multi-batch Emerging Entities
We propose a walk-based inductive reasoning model to tackle the new setting.
I Know What You Do Not Know: Knowledge Graph Embedding via Co-distillation Learning
To this end, we propose CoLE, a Co-distillation Learning method for KG Embedding that exploits the complementarity of graph structures and text information.
Neural Capture of Animatable 3D Human from Monocular Video
We present a novel paradigm of building an animatable 3D human representation from a monocular video input, such that it can be rendered in any unseen poses and views.
Point Cloud Attacks in Graph Spectral Domain: When 3D Geometry Meets Graph Signal Processing
Instead, we propose point cloud attacks from a new perspective -- the graph spectral domain attack, aiming to perturb graph transform coefficients in the spectral domain that corresponds to varying certain geometric structure.
Skimming, Locating, then Perusing: A Human-Like Framework for Natural Language Video Localization
SLP consists of a Skimming-and-Locating (SL) module and a Bi-directional Perusing (BP) module.
Reducing the Vision and Language Bias for Temporal Sentence Grounding
In this paper, we study the above issue of selection biases and accordingly propose a Debiasing-TSG (D-TSG) model to filter and remove the negative biases in both vision and language modalities for enhancing the model generalization ability.
$μ\text{KG}$: A Library for Multi-source Knowledge Graph Embeddings and Applications
It is useful for a thorough comparison and analysis of various embedding models and tasks.
Enhancing Document-level Relation Extraction by Entity Knowledge Injection
Document-level relation extraction (RE) aims to identify the relations between entities throughout an entire document.
Ranked #23 on
Relation Extraction
on DocRED
Facing Changes: Continual Entity Alignment for Growing Knowledge Graphs
To avoid retraining an entire model on the whole KGs whenever new entities and triples come, we present a continual alignment method for this task.
Dynamic Point Cloud Denoising via Gradient Fields
The gradient field is the gradient of the log-probability function of the noisy point cloud, based on which we perform gradient ascent so as to converge each point to the underlying clean surface.
Unsupervised Manga Character Re-identification via Face-body and Spatial-temporal Associated Clustering
In the past few years, there has been a dramatic growth in e-manga (electronic Japanese-style comics).
SAD: A Large-scale Dataset towards Airport Detection in Synthetic Aperture Radar Images
As a result, deep learning methods have not been fully used in airport detection tasks.
Ensemble Semi-supervised Entity Alignment via Cycle-teaching
We also design a conflict resolution mechanism to resolve the alignment conflict when combining the new alignment of an aligner and that from its teacher.
More Than a Toy: Random Matrix Models Predict How Real-World Neural Representations Generalize
On the other hand, we find that the classical GCV estimator (Craven and Wahba, 1978) accurately predicts generalization risk even in such overparameterized settings.
Multi-Scale Self-Contrastive Learning with Hard Negative Mining for Weakly-Supervised Query-based Video Grounding
Secondly, since some predicted frames (i. e., boundary frames) are relatively coarse and exhibit similar appearance to their adjacent frames, we propose a coarse-to-fine contrastive learning paradigm to learn more discriminative frame-wise representations for distinguishing the false positive frames.
Exploring Optical-Flow-Guided Motion and Detection-Based Appearance for Temporal Sentence Grounding
Temporal sentence grounding aims to localize a target segment in an untrimmed video semantically according to a given sentence query.
Sparse Graph Learning with Spectrum Prior for Deep Graph Convolutional Networks
Specifically, based on a spectral analysis of multilayer GCN output, we derive a spectrum prior for the graph Laplacian matrix $\mathbf{L}$ to robustify the model expressiveness against over-smoothing.
Automated Extraction of Energy Systems Information from Remotely Sensed Data: A Review and Analysis
These include the opportunity to extend the methods beyond electricity to broader energy systems and wider geographic areas; and the ability to expand the use of these methods in research and decision making as satellite data become cheaper and easier to access.
Exploring the Devil in Graph Spectral Domain for 3D Point Cloud Attacks
Instead, we propose point cloud attacks from a new perspective -- Graph Spectral Domain Attack (GSDA), aiming to perturb transform coefficients in the graph spectral domain that corresponds to varying certain geometric structure.
Trustworthy Knowledge Graph Completion Based on Multi-sourced Noisy Data
In this paper, we propose a new trustworthy method that exploits facts for a KG based on multi-sourced noisy data and existing facts in the KG.
Informed Multi-context Entity Alignment
Entity alignment is a crucial step in integrating knowledge graphs (KGs) from multiple sources.
Representation Alignment in Neural Networks
We then highlight why alignment between the top singular vectors and the targets can speed up learning and show in a classic synthetic transfer problem that representation alignment correlates with positive and negative transfer to similar and dissimilar tasks.
Imperceptible Transfer Attack and Defense on 3D Point Cloud Classification
Although many efforts have been made into attack and defense on the 2D image domain in recent years, few methods explore the vulnerability of 3D models.
Deep Point Set Resampling via Gradient Fields
3D point clouds acquired by scanning real-world objects or scenes have found a wide range of applications including immersive telepresence, autonomous driving, surveillance, etc.
Principled Representation Learning for Entity Alignment
Embedding-based entity alignment (EEA) has recently received great attention.
Vis-TOP: Visual Transformer Overlay Processor
Vis-TOP summarizes the characteristics of all visual Transformer models and implements a three-layer and two-level transformation structure that allows the model to be switched or changed freely without changing the hardware architecture.
Knowing False Negatives: An Adversarial Training Method for Distantly Supervised Relation Extraction
Distantly supervised relation extraction (RE) automatically aligns unstructured text with relation instances in a knowledge base (KB).
Score-Based Point Cloud Denoising
Since $p * n$ is unknown at test-time, and we only need the score (i. e., the gradient of the log-probability function) to perform gradient ascent, we propose a neural network architecture to estimate the score of $p * n$ given only noisy point clouds as input.
RGB Image Classification with Quantum Convolutional Ansaetze
With the rapid growth of qubit numbers and coherence times in quantum hardware technology, implementing shallow neural networks on the so-called Noisy Intermediate-Scale Quantum (NISQ) devices has attracted a lot of interest.
Self-Contrastive Learning with Hard Negative Sampling for Self-supervised Point Cloud Learning
Point clouds have attracted increasing attention.
A Representation Learning Perspective on the Importance of Train-Validation Splitting in Meta-Learning
An effective approach in meta-learning is to utilize multiple "train tasks" to learn a good initialization for model parameters that can help solve unseen "test tasks" with very few samples by fine-tuning from this initialization.
Near-Optimal Linear Regression under Distribution Shift
Transfer learning is essential when sufficient data comes from the source domain, with scarce labeled data from the target domain.
Knowing the No-match: Entity Alignment with Dangling Cases
Since KGs possess different sets of entities, there could be entities that cannot find alignment across them, leading to the problem of dangling entities.
Ranked #1 on
Entity Alignment
on DBP2.0 zh-en
Self-Supervised Graph Representation Learning via Topology Transformations
We formalize the proposed model from an information-theoretic perspective, by maximizing the mutual information between topology transformations and node representations before and after the transformations.
Learning Fine-grained Fact-Article Correspondence in Legal Cases
We believe that learning fine-grained correspondence between each single fact and law articles is crucial for an accurate and trustworthy AI system.
Diffusion Probabilistic Models for 3D Point Cloud Generation
We present a probabilistic model for point cloud generation, which is fundamental for various 3D vision tasks such as shape completion, upsampling, synthesis and data augmentation.
Self-Supervised Multi-View Learning via Auto-Encoding 3D Transformations
Then, we self-train a representation to capture the intrinsic 3D object representation by decoding 3D transformation parameters from the fused feature representations of multiple views before and after the transformation.
AGRNet: Adaptive Graph Representation Learning and Reasoning for Face Parsing
Face parsing infers a pixel-wise label to each facial component, which has drawn much attention recently.
Ranked #3 on
Face Parsing
on CelebAMask-HQ
A Point Cloud Generative Model Based on Nonequilibrium Thermodynamics
Point cloud generation thus amounts to learning the reverse diffusion process that transforms the noise distribution to the distribution of a desired shape.
Towards Principled Representation Learning for Entity Alignment
In this paper, we define a typical paradigm abstracted from the existing methods, and analyze how the representation discrepancy between two potentially-aligned entities is implicitly bounded by a predefined margin in the scoring function for embedding learning.
TopoTER: Unsupervised Learning of Topology Transformation Equivariant Representations
We formalize the TopoTER from an information-theoretic perspective, by maximizing the mutual information between topology transformations and node representations before and after the transformations.
A Unified Model for Gate Level Propagation Analysis
To justify our model, we prove that Precise Hardware IFT is equivalent to gate level X-propagation and imprecise fault propagation.
Hardware Architecture
Eudoxus: Characterizing and Accelerating Localization in Autonomous Machines
We develop and commercialize autonomous machines, such as logistic robots and self-driving cars, around the globe.
Self-Driving Cars
Hardware Architecture
AdCo: Adversarial Contrast for Efficient Learning of Unsupervised Representations from Self-Trained Negative Adversaries
Contrastive learning relies on constructing a collection of negative examples that are sufficiently hard to discriminate against positive queries when their representations are self-trained.
Impact of Representation Learning in Linear Bandits
For the finite-action setting, we present a new algorithm which achieves $\widetilde{O}(T\sqrt{kN} + \sqrt{dkNT})$ regret, where $N$ is the number of rounds we play for each bandit.
Knowledge Association with Hyperbolic Knowledge Graph Embeddings
Capturing associations for knowledge graphs (KGs) through entity alignment, entity type inference and other related tasks benefits NLP applications with comprehensive knowledge representations.
Ranked #28 on
Entity Alignment
on DBP15k zh-en
Global-to-Local Neural Networks for Document-Level Relation Extraction
Relation extraction (RE) aims to identify the semantic relations between named entities in text.
Ranked #39 on
Relation Extraction
on DocRED
P-DIFF: Learning Classifier with Noisy Labels based on Probability Difference Distributions
Learning deep neural network (DNN) classifier with noisy labels is a challenging task because the DNN can easily over-fit on these noisy labels due to its high capability.
Rule-Guided Graph Neural Networks for Recommender Systems
However, existing work incorporated with KGs cannot capture the explicit long-range semantics between users and items meanwhile consider various connectivity between items.
Graph Signal Processing for Geometric Data and Beyond: Theory and Applications
Geometric data acquired from real-world scenes, e. g., 2D depth images, 3D point clouds, and 4D dynamic point clouds, have found a wide range of applications including immersive telepresence, autonomous driving, surveillance, etc.
Differentiable Manifold Reconstruction for Point Cloud Denoising
Afterwards, the decoder infers the underlying manifold by transforming each sampled point along with the embedded feature of its neighborhood to a local surface centered around the point.
Edge-aware Graph Representation Learning and Reasoning for Face Parsing
Specifically, we encode a facial image onto a global graph representation where a collection of pixels ("regions") with similar features are projected to each vertex.
Ranked #4 on
Face Parsing
on CelebAMask-HQ
The Surprising Simplicity of the Early-Time Learning Dynamics of Neural Networks
Modern neural networks are often regarded as complex black-box functions whose behavior is difficult to understand owing to their nonlinear dependence on the data and the nonconvexity in their loss landscapes.
Signed Graph Metric Learning via Gershgorin Disc Perfect Alignment
Given a convex and differentiable objective $Q(\M)$ for a real symmetric matrix $\M$ in the positive definite (PD) cone -- used to compute Mahalanobis distances -- we propose a fast general metric learning framework that is entirely projection-free.
When is Particle Filtering Efficient for Planning in Partially Observed Linear Dynamical Systems?
Though errors in past actions may affect the future, we are able to bound the number of particles needed so that the long-run reward of the policy based on particle filtering is close to that based on exact inference.
TransEdge: Translating Relation-contextualized Embeddings for Knowledge Graphs
We refer to such contextualized representations of a relation as edge embeddings and interpret them as translations between entity embeddings.
Realistic Re-evaluation of Knowledge Graph Completion Methods: An Experimental Study
A more fundamental defect of these models is that the link prediction scenario, given such data, is non-existent in the real-world.
Dynamic Point Cloud Denoising via Manifold-to-Manifold Distance
In particular, we define a manifold-to-manifold distance and its discrete counterpart on graphs to measure the variation-based intrinsic distance between surface patches in the temporal domain, provided that graph operators are discrete counterparts of functionals on Riemannian manifolds.
A Benchmarking Study of Embedding-based Entity Alignment for Knowledge Graphs
Recent advancement in KG embedding impels the advent of embedding-based entity alignment, which encodes entities in a continuous embedding space and measures entity similarities based on the learned embeddings.
Crowdsourced Collective Entity Resolution with Relational Match Propagation
Knowledge bases (KBs) store rich yet heterogeneous entities and facts.
Few-Shot Learning via Learning the Representation, Provably
First, we study the setting where this common representation is low-dimensional and provide a fast rate of $O\left(\frac{\mathcal{C}\left(\Phi\right)}{n_1T} + \frac{k}{n_2}\right)$; here, $\Phi$ is the representation function class, $\mathcal{C}\left(\Phi\right)$ is its complexity measure, and $k$ is the dimension of the representation.
Open Knowledge Enrichment for Long-tail Entities
In this paper, we propose a full-fledged approach to knowledge enrichment, which predicts missing properties and infers true facts of long-tail entities from the open Web.
Graph Metric Learning via Gershgorin Disc Alignment
We propose a fast general projection-free metric learning framework, where the minimization objective $\min_{\textbf{M} \in \mathcal{S}} Q(\textbf{M})$ is a convex differentiable function of the metric matrix $\textbf{M}$, and $\textbf{M}$ resides in the set $\mathcal{S}$ of generalized graph Laplacian matrices for connected graphs with positive edge weights and node degrees.
Provable Benefit of Orthogonal Initialization in Optimizing Deep Linear Networks
The selection of initial parameter values for gradient-based optimization of deep neural networks is one of the most impactful hyperparameter choices in deep learning systems, affecting both convergence times and model performance.
3D Hand Pose Estimation via Regularized Graph Representation Learning
To this end, we propose a regularized graph representation learning under a conditional adversarial learning framework for 3D hand pose estimation, aiming to capture structural inter-dependencies of hand joints.
Knowledge Graph Alignment Network with Gated Multi-hop Neighborhood Aggregation
As the direct neighbors of counterpart entities are usually dissimilar due to the schema heterogeneity, AliNet introduces distant neighbors to expand the overlap between their neighborhood structures.
Ranked #29 on
Entity Alignment
on DBP15k zh-en
GraphTER: Unsupervised Learning of Graph Transformation Equivariant Representations via Auto-Encoding Node-wise Transformations
Recent advances in Graph Convolutional Neural Networks (GCNNs) have shown their efficiency for non-Euclidean data on graphs, which often require a large amount of labeled data with high cost.
Enhanced Convolutional Neural Tangent Kernels
An exact algorithm to compute CNTK (Arora et al., 2019) yielded the finding that classification accuracy of CNTK on CIFAR-10 is within 6-7% of that of that of the corresponding CNN architecture (best figure being around 78%) which is interesting performance for a fixed kernel.
Joint Learning of Graph Representation and Node Features in Graph Convolutional Neural Networks
In particular, we cast the graph optimization problem as distance metric learning to capture pairwise similarities of features in each layer.
Leveraging Frequent Query Substructures to Generate Formal Queries for Complex Question Answering
Formal query generation aims to generate correct executable queries for question answering over knowledge bases (KBs), given entity and relation linking results.
Feature Graph Learning for 3D Point Cloud Denoising
In this work, we assume instead the availability of a relevant feature vector $\mathbf{f}_i$ per node $i$, from which we compute an optimal feature graph via optimization of a feature metric.
Explaining Landscape Connectivity of Low-cost Solutions for Multilayer Nets
Mode connectivity is a surprising phenomenon in the loss landscape of deep nets.
Multi-view Knowledge Graph Embedding for Entity Alignment
Furthermore, we design some cross-KG inference methods to enhance the alignment between two KGs.
Implicit Regularization in Deep Matrix Factorization
Efforts to understand the generalization mystery in deep learning have led to the belief that gradient-based optimization induces a form of implicit regularization, a bias towards models of low "complexity."
Simple and Effective Regularization Methods for Training on Noisily Labeled Data with Generalization Guarantee
Over-parameterized deep neural networks trained by simple first-order methods are known to be able to fit any labeling of data.
Learning to Exploit Long-term Relational Dependencies in Knowledge Graphs
Moreover, triple-level learning is insufficient for the propagation of semantic information among entities, especially for the case of cross-KG embedding.
3D Dynamic Point Cloud Denoising via Spatial-Temporal Graph Learning
Finally, based on the spatial-temporal graph learning, we formulate dynamic point cloud denoising as the joint optimization of the desired point cloud and underlying spatio-temporal graph, which leverages both intra-frame affinities and inter-frame consistency and is solved via alternating minimization.
On Exact Computation with an Infinitely Wide Neural Net
An attraction of such ideas is that a pure kernel-based method is used to capture the power of a fully-trained deep net of infinite width.
Exploring Structure-Adaptive Graph Learning for Robust Semi-Supervised Classification
In this paper, we propose Graph Learning Neural Networks (GLNNs), which exploit the optimization of graphs (the adjacency matrix in particular) from both data and tasks.
3D Dynamic Point Cloud Inpainting via Temporal Consistency on Graphs
With the development of 3D laser scanning techniques and depth sensors, 3D dynamic point clouds have attracted increasing attention as a representation of 3D objects in motion, enabling various applications such as 3D immersive tele-presence, gaming and navigation.
Noise-Tolerant Paradigm for Training Face Recognition CNNs
Benefit from large-scale training datasets, deep Convolutional Neural Networks(CNNs) have achieved impressive results in face recognition(FR).
What you get is not always what you see: pitfalls in solar array assessment using overhead imagery
Our findings suggest that traditional performance evaluation of the automated identification of solar PV from satellite imagery may be optimistic due to common limitations in the validation process.
Width Provably Matters in Optimization for Deep Linear Neural Networks
We prove that for an $L$-layer fully-connected linear neural network, if the width of every hidden layer is $\tilde\Omega (L \cdot r \cdot d_{\mathrm{out}} \cdot \kappa^3 )$, where $r$ and $\kappa$ are the rank and the condition number of the input data, and $d_{\mathrm{out}}$ is the output dimension, then gradient descent with Gaussian random initialization converges to a global minimum at a linear rate.
Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks
This paper analyzes training and generalization for a simple 2-layer ReLU net with random initialization, and provides the following improvements over recent works: (i) Using a tighter characterization of training speed than recent papers, an explanation for why training a neural net with random labels leads to slower training, as originally observed in [Zhang et al. ICLR'17].
Feature Preserving and Uniformity-controllable Point Cloud Simplification on Graph
With the development of 3D sensing technologies, point clouds have attracted increasing attention in a variety of applications for 3D object representation, such as autonomous driving, 3D immersive tele-presence and heritage reconstruction.
Optimized Skeleton-based Action Recognition via Sparsified Graph Regression
In this paper, we represent skeletons naturally on graphs, and propose a graph regression based GCN (GR-GCN) for skeleton-based action recognition, aiming to capture the spatio-temporal variation in the data.
Ranked #2 on
Skeleton Based Action Recognition
on Florence 3D
Exploring Hypergraph Representation on Face Anti-spoofing Beyond 2D Attacks
Face anti-spoofing plays a crucial role in protecting face recognition systems from various attacks.
Recurrent Skipping Networks for Entity Alignment
We consider the problem of learning knowledge graph (KG) embeddings for entity alignment (EA).
DSKG: A Deep Sequential Model for Knowledge Graph Completion
Knowledge graph (KG) completion aims to fill the missing facts in a KG, where a fact is represented as a triple in the form of $(subject, relation, object)$.
A Convergence Analysis of Gradient Descent for Deep Linear Neural Networks
We analyze speed of convergence to global optimum for gradient descent training a deep linear neural network (parameterized as $x \mapsto W_N W_{N-1} \cdots W_1 x$) by minimizing the $\ell_2$ loss over whitened data.
Local Frequency Interpretation and Non-Local Self-Similarity on Graph for Point Cloud Inpainting
Hence, leveraging on recent advances in graph signal processing, we propose an efficient point cloud inpainting method, exploiting both the local smoothness and the non-local self-similarity in point clouds.
Matrix Linear Discriminant Analysis
We propose a novel linear discriminant analysis approach for the classification of high-dimensional matrix-valued data that commonly arises from imaging studies.
RGCNN: Regularized Graph CNN for Point Cloud Segmentation
Leveraging on spectral graph theory, we treat features of points in a point cloud as signals on graph, and define the convolution over graph by Chebyshev polynomial approximation.
Algorithmic Regularization in Learning Deep Homogeneous Models: Layers are Automatically Balanced
Using a discretization argument, we analyze gradient descent with positive step size for the non-convex low-rank asymmetric matrix factorization problem without any regularization.
TreeSegNet: Adaptive Tree CNNs for Subdecimeter Aerial Image Segmentation
For the task of subdecimeter aerial imagery segmentation, fine-grained semantic segmentation results are usually difficult to obtain because of complex remote sensing content and optical conditions.
Online Improper Learning with an Approximation Oracle
We revisit the question of reducing online learning to approximate optimization of the offline problem.
SeqFace: Make full use of sequence information for face recognition
Deep convolutional neural networks (CNNs) have greatly improved the Face Recognition (FR) performance in recent years.
Ranked #1 on
Face Verification
on YouTube Faces DB
An Analysis of the t-SNE Algorithm for Data Visualization
A first line of attack in exploratory data analysis is data visualization, i. e., generating a 2-dimensional representation of data that makes clusters of similar points visually identifiable.
Linear Convergence of the Primal-Dual Gradient Method for Convex-Concave Saddle Point Problems without Strong Convexity
We consider the convex-concave saddle point problem $\min_{x}\max_{y} f(x)+y^\top A x-g(y)$ where $f$ is smooth and convex and $g$ is smooth and strongly convex.
Nearly Optimal Dynamic $k$-Means Clustering for High-Dimensional Data
We consider the $k$-means clustering problem in the dynamic streaming setting, where points from a discrete Euclidean space $\{1, 2, \ldots, \Delta\}^d$ can be dynamically inserted to or deleted from the dataset.
DeepUNet: A Deep Fully Convolutional Network for Pixel-level Sea-Land Segmentation
Semantic segmentation is a fundamental research in remote sensing image processing.
Cross-lingual Entity Alignment via Joint Attribute-Preserving Embedding
Our experimental results on real-world datasets show that this approach significantly outperforms the state-of-the-art embedding approaches for cross-lingual entity alignment and could be complemented with methods based on machine translation.
Linear Convergence of a Frank-Wolfe Type Algorithm over Trace-Norm Balls
We propose a rank-$k$ variant of the classical Frank-Wolfe algorithm to solve convex optimization over a trace-norm ball.
PDD Graph: Bridging Electronic Medical Records and Biomedical Knowledge Graphs via Entity Linking
Electronic medical records contain multi-format electronic medical data that consist of an abundance of medical knowledge.
Combinatorial Multi-Armed Bandit with General Reward Functions
Our framework enables a much larger class of reward functions such as the $\max()$ function and nonlinear utility functions.
Real-time Decolorization using Dominant Colors
Decolorization is the process to convert a color image or video to its grayscale version, and it has received great attention in recent years.
